# Multi-hop Question Answering on LooGLE CR 16k

Source: [Multi-hop Question Answering on LooGLE CR 16k](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-loogle-cr-16k>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:03:48.613Z

Evaluation of model performance on the LooGLE CR 16k dataset for Multi-hop Question Answering, reporting Score and Avg. metrics.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Multi-hop Question Answering |
| Dataset (including any stated split) | LooGLE CR 16k |
| Metric | Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Score](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-loogle-cr-16k.md?metric=Score>): Higher is better; unit: PERCENT.

- [Average Performance](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-loogle-cr-16k.md?metric=Average%20Performance>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| Llama-3-8B-Instruct with DCS | 19.78 | Not recorded | 68fa79171e209131cea7c13c |
| Llama-3-8B-Instruct | 16.49 | Not recorded | 68fa79171e209131cea7c13c |
| Llama-3-8B-Instruct with Infillm | 15.55 | Not recorded | 68fa79171e209131cea7c13c |
| Llama-3-8B-Instruct with Streaming | 14.5 | Not recorded | 68fa79171e209131cea7c13c |
| Llama-3-8B-Instruct with LM-infinite | 14.26 | Not recorded | 68fa79171e209131cea7c13c |

### Llama-3-8B-Instruct with DCS

Score: 19.78. Result ID: 6995c5743badfaffe6c8baeb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79171e209131cea7c13c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79171e209131cea7c13c.md>)

[Implementation](<https://github.com/ECNU-Text-Computing/DCS>)

Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct","Context Strategy":"DCS"}. This record does not assert independent reproduction.

### Llama-3-8B-Instruct

Score: 16.49. Result ID: 6995c5743badfaffe6c8bae7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79171e209131cea7c13c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct","Context Strategy":"None"}. This record does not assert independent reproduction.

### Llama-3-8B-Instruct with Infillm

Score: 15.55. Result ID: 6995c5743badfaffe6c8baea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79171e209131cea7c13c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa736c1e209131cea5c6bf.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct","Context Strategy":"Infillm"}. This record does not assert independent reproduction.

### Llama-3-8B-Instruct with Streaming

Score: 14.5. Result ID: 6995c5743badfaffe6c8bae8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79171e209131cea7c13c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d71e209131cea58d79.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct","Context Strategy":"Streaming"}. This record does not assert independent reproduction.

### Llama-3-8B-Instruct with LM-infinite

Score: 14.26. Result ID: 6995c5743badfaffe6c8bae9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79171e209131cea7c13c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73e01e209131cea5e9a9.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3-8B-Instruct","Context Strategy":"LM-infinite"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.